Numerous theories and algorithms have been developed to solve vectorial data learning problems by searching for the hypothesis that best fits the observed training sample. However, many real-world applications involve samples that are not described as feature vectors, but as (dis)similarity data. Converting vectorial data into (dis)similarity data is more easily performed than converting (dis)similarity data into vectorial data. This study proposes a stochastic iterative distance transformation model for similarity-based learning. The proposed model can be used to identify a clear class boundary in data by modifying the (dis)similarities between examples. The experimental results indicate that the performance of the proposed method is comparable with those of various vector-based and proximity-based learning algorithms.

In this article, we present a content-based video search service for mobile device users. After taking a photograph, the user can upload it to our server, which will then return videos containing key frames that are similar to the uploaded picture. The proposed service demonstrates that the search application is feasible.

Nowadays, many people started to produce personal web pages, and most web pages contain multimedia content. However, there are some problems with the design of web content, the web editor provided by web pages is very inconvenient, and there also exists the inconsistent problem on web content when the content had been accessed. To resolve these problems, we propose a multimedia on-line editing technique that enables users to edit web content and add comments on-line. In addition, web content on different web sites can be easily accessed by our system. The original web content that is accessed can be updated at the same time so that both versions are the same. The proposed system can also be used to e-learning. This function helps people who produce abundance and a large number of teaching materials, and it facilitates interaction and communication among users.